mvoelk/ssd_detectors

How to use

wander1985 opened this issue · 5 comments

wander1985 commented

Hello, sir, thanks for this excellent work. I am a newcomer for text detection and recognition. I followed your instruction from the "Usage" part, but I just cannot run any scripts successfully at all. It seems a lot of datasets need to be pre-installed.
Can you provide some more specific explanations on how to use this code? or a simple example for the user to reproduce the process will also be very helpful. Thanks for your efforts.

mvoelk commented

Please read the issues. I hope you find answers to your questions in #3 and #11.

I intend to add more documentation and clean up the code as soon as I find the time.

wander1985 commented

Please read the issues. I hope you find answers to your questions in #3 and #11.

I intend to add more documentation and clean up the code as soon as I find the time.

Great, thanks!

anindya7 commented

Hi, this is a fantastic project and would be of great help to me. On trying to run the notebooks I see that the checkpoint files are not there. Would you have the time to please add some notes on running the pre-trained models for predictions? My greatest interest is in obtaining the output in the demo video at the end of the Readme. How may I run that detector?
Thanks in advance.

mvoelk commented

@anindya7 The links to the pre-trained models can be found in the README.md. Extract the archives to the appropriate directory or change the path in the python code.

mvoelk commented

The code in the *end2end* files is probably not up to date for TensorFlow 2.x and needs to be updated. The tf1 branch should work with TensorFlow 1.x